paper-with-me

Papers

Sample-Efficient Diffusion for Text-To-Speech Synthesis

2024-09-01 · Justin Lovelace, Soham Ray, Kwangyoun Kim, Kilian Q. Weinberger, Felix Wu

This work introduces Sample-Efficient Speech Diffusion (SESD), an algorithm for effective speech synthesis in modest data regimes through latent diffusion. It is based on a novel diffusion architecture, that we call U-Audio Transformer (U-AT), that efficiently scales to long sequences and operates in the latent space of a pre-trained audio autoencoder. Conditioned on character-aware language model representations, SESD achieves impressive results despite training on less than 1k hours of speech - far less than current state-of-the-art systems. In fact, it synthesizes more intelligible speech than the state-of-the-art auto-regressive model, VALL-E, while using less than 2% the training data.

📄 PDF Abstract BibTeX arXiv:2409.03717

Code (1)

justinlovelace/sesd 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingSpeech Synthesistext-to-speechText to SpeechText-To-Speech Synthesis

Methods 이 논문이 사용한 방법론

Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model

2023-05-11 · Zhen Ye, Wei Xue, Xu Tan, Jie Chen 외

Denoising diffusion probabilistic models (DDPMs) have shown promising performance for speech synthesis. However, a large number of iterative steps are required to achieve high sample quality, which restricts the inferenc…

DenoisingGPUSinging Voice SynthesisSpeech Synthesis+2

FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis

2022-04-21 · Rongjie Huang, Max W. Y. Lam, Jun Wang, Dan Su 외

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthes…

DenoisingGPUSpeech Synthesistext-to-speech+3

DiffCSS: Diverse and Expressive Conversational Speech Synthesis with Diffusion Models

2025-02-27 · Weihao wu, Zhiwei Lin, Yixuan Zhou, Jingbei Li 외

Conversational speech synthesis (CSS) aims to synthesize both contextually appropriate and expressive speech, and considerable efforts have been made to enhance the understanding of conversational context. However, exist…

DiversityLanguage ModelingLanguage ModellingSpeech Synthesis

DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs

2022-01-28 · Songxiang Liu, Dan Su, Dong Yu

Denoising diffusion probabilistic models (DDPMs) are expressive generative models that have been used to solve a variety of speech synthesis problems. However, because of their high sampling costs, DDPMs are difficult to…

DenoisingSpeech Synthesistext-to-speechText to Speech

CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models

2024-03-31 · Xiang Li, Fan Bu, Ambuj Mehrish, Yingting Li 외

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, r…

DenoisingSpeech Synthesistext-to-speechText to Speech+1